SLA Threat Analytics

Legacy approaches no longer work to protect against SLA abuse.

Mobile providers lose $6.11 billion to roaming fraud each year.

Roaming fraud is the responsibility of the home network of the subscriber, providing that the visiting network meets its Service Level Agreement (SLA) commitments (typically 4 hours). This time window is critical, because:

  • If the SLA is met the financial responsibility is in the hands of the home network.
  • If the SLA is not met the financial responsibility is in the hands of the visiting network.

This is truly a big data problem as it involves intelligently combining:

  • Machine learning to detect fraud threats
  • Roaming data feeds for every other network in the world
  • Matching time periods – every other network sends multiple files per day
  • CRM data
  • Billing data

Often this is just too complex or labor intensive to do, so a home network takes the financial penalty, even when it is not responsible because the partner has not met their SLA requirements.

This situation is made worse as cyber-criminals know which partners are bad at meeting their SLA and exploit the larger window of opportunity for fraud – often calling high-cost, international revenue share, premium rate numbers.

What’s wrong with legacy systems?

  • Legacy approaches are too slow and labor-intensive to validate fraud across multiple fraud, network, CRM, and billing systems. These are essential in order to validate fraud and SLA compliance.
  • The home network often takes too much fiscal responsibility for fraud when SLAs are not met.

Use SLA Threat Analytics to get a multi-million dollar return by integrating multiple systems and properly allocating financial responsibility.

Argyle Data delivers a “SLA Threat Analytics” application that combines massive amounts of roaming data, real-time network data, and business data in one simple-to-use dashboard.

Argyle’s native Hadoop application incorporates:

Machine Learning

  • The latest machine learning techniques allow you to discover threats more easily by detecting and visualizing sophisticated attacks – both known and new, unknown threats.

Fraud Threat Scoring

  • With legacy systems, analysts often waste time on false positives. Our machine learning-driven fraud threat scoring prioritizes fraud attacks, allowing analysts to effectively use their time inspecting real threats.

Integrated Application

  • Our integrated applications allow analysts to simply combine fraud, profit, and SLA threats.

Argyle Data’s “SLA Threat Analytics” application provides the following call data:

  • In SLA
  • Out of SLA
  • Invalid time or data

Argyle Data’s “SLA Threat Analytics” application provides the following operator data:

  • Number of calls out of SLA
  • Percentage of calls out of SLA
  • Combined hours delay
  • Over 100 hours delay
  • Incorrect file count

Request a Demo

Get Our E-Book